Video · Tech With Tim ·
I Tested the Cheapest Coding Model on 7 Real Builds
In short
The video tests MiniMax M3.1 Flash on seven coding projects plus a larger Figma clone, using iterative agent runs capped at $1 per project and $10 for the final build. It demonstrates that the model can produce surprisingly capable apps quickly and cheaply, making it a practical option for AI-assisted coding when frontier-model costs matter.
Key points
- MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens, versus Claude Opus at $4 and $20.
- The model ran at roughly 195 to 222 tokens per second and supports a 1-million-token context window.
- Seven $1 builds included Neon Dash, a Chrome summarizer extension, data analysis, a Kahoot clone, an existing-app upgrade, a web operating system, and Blockcraft.
- The model built a collaborative Figma-style app called Canvas for $3.52 after six build-and-revision sessions.
- The complete experiment cost $10.60, compared with an estimated $215 for the same token usage with Opus 5.5.
- The video concludes that M3.1 Flash offers strong agentic coding performance at a fraction of frontier-model costs.
Written by an AI model from the video’s captions and description.
So I wanted to see what all the hype was about. In this video, we put MiniMax M3.1 Flash to the test, explore its coding capabilities, and see what it can actually build.



